activity
20182021
most citedAuto-tuning of Deep Neural Networks by Conflicting Layer Removal

1 citations · 1 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CV2021

Training Deep Capsule Networks with Residual Connections

Josef Gugglberger, David Peer, Antonio Rodriguez-Sanchez

Capsule networks are a type of neural network that have recently gained increased popularity. They consist of groups of neurons, called capsules, which encode properties of objects…

cs.LG20211 cited

Auto-tuning of Deep Neural Networks by Conflicting Layer Removal

David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez

Designing neural network architectures is a challenging task and knowing which specific layers of a model must be adapted to improve the performance is almost a mystery. In this pa…

cs.CV2021

Arguments for the Unsuitability of Convolutional Neural Networks for Non--Local Tasks

Sebastian Stabinger, David Peer, Antonio Rodríguez-Sánchez

Convolutional neural networks have established themselves over the past years as the state of the art method for image classification, and for many datasets, they even surpass huma…

cs.LG2020

Conflicting Bundles: Adapting Architectures Towards the Improved Training of Deep Neural Networks

David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez

Designing neural network architectures is a challenging task and knowing which specific layers of a model must be adapted to improve the performance is almost a mystery. In this pa…

cs.LG2019

Limitation of capsule networks

David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez

A recently proposed method in deep learning groups multiple neurons to capsules such that each capsule represents an object or part of an object. Routing algorithms route the outpu…

cs.LG2018

Increasing the adversarial robustness and explainability of capsule networks with -capsules

David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez

In this paper we introduce a new inductive bias for capsule networks and call networks that use this prior -capsule networks. Our inductive bias that is inspired by TE neurons o…